MASON: A Model AgnoStic ObjectNess Framework

K. J. Joseph, Rajiv Chunilal Patel, Amit Srivastava, Uma Gupta, Vineeth N. Balasubramanian

ECCVW 2018 pp. 642-658

doi:10.1007/978-3-030-11021-5_40 /eccvw/2018/joseph2018eccvw-mason/

Abstract

This paper proposes a simple, yet very effective method to localize dominant foreground objects in an image, to pixel-level precision. The proposed method ‘MASON’ (Model-AgnoStic ObjectNess) uses a deep convolutional network to generate category-independent and model-agnostic heat maps for any image. The network is not explicitly trained for the task, and hence, can be used off-the-shelf in tandem with any other network or task. We show that this framework scales to a wide variety of images, and illustrate the effectiveness of MASON in three varied application contexts.

PDF ECCVW Semantic Scholar

Cite

Text

Joseph et al. "MASON: A Model AgnoStic ObjectNess Framework." European Conference on Computer Vision Workshops, 2018. doi:10.1007/978-3-030-11021-5_40

Markdown

[Joseph et al. "MASON: A Model AgnoStic ObjectNess Framework." European Conference on Computer Vision Workshops, 2018.](https://mlanthology.org/eccvw/2018/joseph2018eccvw-mason/) doi:10.1007/978-3-030-11021-5_40

BibTeX

@inproceedings{joseph2018eccvw-mason,
  title     = {{MASON: A Model AgnoStic ObjectNess Framework}},
  author    = {Joseph, K. J. and Patel, Rajiv Chunilal and Srivastava, Amit and Gupta, Uma and Balasubramanian, Vineeth N.},
  booktitle = {European Conference on Computer Vision Workshops},
  year      = {2018},
  pages     = {642-658},
  doi       = {10.1007/978-3-030-11021-5_40},
  url       = {https://mlanthology.org/eccvw/2018/joseph2018eccvw-mason/}
}